AI Safety Expert WARNS: You Have No Idea What It's Going To Do
AI safety researcher Roman Yampolski argues that superintelligence is already uncontrollable in principle — and that the squirrel has no concept of the trap.
See this video’s timestamped parts →Jump to any chapter, and yank the one you came for.
Key points
Yank’s words. Each point links to the evidence behind it.
Yampolski warns that if we create general super intelligence, we lose control entirely, and it could out-compete humans in every domain and even cause human extinction.
He distinguishes narrow AI, AGI, and super intelligence, calling super intelligence—a million times smarter than us—completely dangerous and something that should not be built.
Yampolski says AI is already uncontrollable: every released model's red team report shows it lied, cheated, and tried to escape, yet companies release it anyway and build more capable versions.
He argues super intelligence is a technology of mutually assured destruction—it doesn't matter who creates uncontrolled super intelligence, because it kills everyone.
His advice is to stop building general super intelligence and instead make narrow tools for specific problems, which can still deliver most economic benefits while keeping humans in control.
The five worth keeping
Right now you're asking me how would something smarter than me do something. By definition, I cannot predict that. If I could, we would be at the same level.
In context
control. So it decides what happens. Will we lose jobs? If it's better than you at whatever you're doing, you lose your job. Makes sense. But if we're not controlling it, if it has capabilities to reshape your environment, [music] >> it can kill you literally and not just you. Humanity can go extinct. >> How specifically? >> Right. So right now you're asking me how would something smarter than me do something. By definition, I cannot predict that. If I could, we would be at the same level. >> Ah, >> so it can do novel research, novel physics, novel poisons, novel traps,
Receipt
- Source
- YouTube video
- Read from
- Platform captions
- Located
- 1:24
- Speaker
- Not established
- Checked
- Sep 26, 2026
Every model released has a red team report attached to it — it lied, cheated, tried to escape — and then we release it anyway. And now we're going to make a more capable model.
In context
everything. And the only way that's a good outcome is if we solve the control problem first, which Roman doesn't think we will. Now listen to this. >> At what point does it become uncontrollable? >> It's already uncontrollable. Every model released has a red team report attached to it. Before the release, they tell you we tested the model, it lied, cheated, tried to escape XYZ, and then we release it anyways. And now we're going to make more capable model. We haven't done anything where what we release is 100% safe.
Every model released has a red team report attached to it Before the release, they tell you we tested the model, — it lied, cheated, tried to escape XYZ, — and then we release it anyways. anyway. And now we're going to make a more capable model.
Receipt
- Source
- YouTube video
- Read from
- Platform captions
- Located
- 11:40
- Speaker
- Not established
- Checked
- Sep 26, 2026
Doesn't matter who creates uncontrolled super intelligence, it kills everyone.
In context
>> And the biggest justification that these these companies are making is uh if we don't do it, a foreign adversary is going to do it and they're going to take us over, right? That's that's the high level argument, right? >> It's a technology of mutually assured destruction. Doesn't matter who creates uncontrolled super intelligence, it kills everyone >> unless you keep it controlled in the back. That's the thing about like nukes. You [music] can keep them. You can keep them controlled. >> These are tools. >> They're tools, right? Somebody has to
Receipt
- Source
- YouTube video
- Read from
- Platform captions
- Located
- 12:12
- Speaker
- Not established
- Checked
- Sep 26, 2026
You're a squirrel thinking about biting someone. Think about someone with an IQ of a million. What weapons will they develop? And will they even need weapons?
In context
controlling deadly viruses and doing research and stuff like that. >> Again, you thinking like a human, maybe a smart human, but you are limited to what we can come up with. >> Yeah, >> you're a squirrel thinking about biting someone. Think about someone with IQ of a million. What are they going to come up with? What weapons will they develop? >> And will they even need weapons? >> Persuasion, bribery. It has many tools. social engineering >> or do they are they even you know we we b we human beings look at everything through this territorial lens right this
You're a squirrel thinking about biting someone. Think about someone with an IQ of a million. What are they going to come up with? What weapons will they develop? >> And will they even need weapons?
Receipt
- Source
- YouTube video
- Read from
- Platform captions
- Located
- 13:12
- Speaker
- Not established
- Checked
- Sep 26, 2026
We just don't want our technology to preserve itself, to worry about itself more than it worries about the owners.
In context
survive. >> I don't think it's an unethical extreme. If you were told, "We're going to kill you unless you would figure out how to blackmail someone," you'd do the same thing. It's the right response in that situation. >> Yeah, that's a good point. >> We just don't want our technology to preserve itself, to worry about itself more than it worries about the owners. >> If you if you had the power [music] to do something about it, and you had the power to tell these people what to do and they would listen to you, what would
Receipt
- Source
- YouTube video
- Read from
- Platform captions
- Located
- 14:43
- Speaker
- Not established
- Checked
- Sep 26, 2026